© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12226
    Prev
    Next
    INDEX
    Explanations

    negative conditions or actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ]))
    -0.82
    但
    -0.81
     aquí
    -0.81
     but
    -0.81
    сель
    -0.76
    ǧ
    -0.76
    herb
    -0.74
     EURO
    -0.73
     Indust
    -0.71
     jedynie
    -0.71
    POSITIVE LOGITS
    veur
    0.91
     declarar
    0.89
     hopeless
    0.84
    нейших
    0.84
    iki
    0.84
     contribute
    0.81
     userManager
    0.80
     perpetuity
    0.79
    バイル
    0.79
    говори
    0.79
    Activations Density 0.087%

    No Known Activations